Abstract

To effectively decarbonize buildings accurate energy models must be created to predict building energy performance. Typical meteorological year (TMY) weather files represent long-term weather conditions and are used in energy modelling to help evaluate energy performance. This thesis explores generating TMY files using machine learning to improve accuracy, which can significantly influence energy simulation results. The current TMY generation approach relies on expert judgment, often overlooking seasonal, climate and application-based variations.
Manuscript #1 introduces a machine learning methodology using feature importance to determine the relevant generation parameters used in the Sandia method to enhance the current TMY generation approach. The proposed methodology is applied to a medium office building in Montreal. The results reveal an improved representativeness of the long-term average building energy demand for the TMY generated using the proposed methodology.
Manuscript #2 aims to (1) assess the applicability of the methodology across Canadian climates; (2) investigate the feasibility of using standardized climate zone-based weighting factors to reduce the computational time associated with extracting location-based weighting factors to facilitate wider adoption of the proposed methodology. The methodology is applied to 18 cities across six Canadian climate zones and generates two weather files for each location. TMYSTATION uses location-based weighting factors while TMYCZ uses climate zone-based weighting factors. The CV(RMSE) and NMBE indicate the proposed weather files outperform the conventional weather files in predicting the long-term energy performance of buildings. Although the TMYSTATION files performed marginally better, the convenience of standardized climate zone-based weighting factors can enhance the methodology’s adaptability.